Legal claims defining the scope of protection, as filed with the USPTO.
1. A method comprising: determining, by a processor deployed in a network function virtualization infrastructure, an amount of resources consumed by a virtual network function subsequent to a scaling of the amount of the resources in response to an occurrence of a predefined trigger event; determining, by the processor, a difference between the amount of resources consumed by the virtual network function subsequent to the scaling and an estimated resource capacity associated with the predefined trigger event; determining, by the processor, a value of a key performance indicator for the virtual network function subsequent to a completion of the scaling; evaluating, by the processor, an efficiency of the predefined trigger event that triggers the scaling, based on the amount of the resources consumed by the virtual network function subsequent to the scaling and the key performance indicator for the virtual network function subsequent to the completion of the scaling; and adjusting, by the processor, the predefined trigger event based on the evaluating.
2. The method of claim 1 , wherein the predefined trigger event caused the scaling to occur in response to a traffic load processed by the virtual network function exceeding a predefined threshold.
3. The method of claim 2 , wherein the traffic load comprises a number of concurrent sessions being processed by the virtual network function.
4. The method of claim 2 , wherein the traffic load comprises a number of packets per second being processed by the virtual network function.
5. The method of claim 1 , wherein the predefined trigger event caused the scaling to occur in response to the value of the key performance indicator falling below a predefined threshold.
6. The method of claim 1 , wherein the predefined trigger event caused the scaling to occur in response to the value of the key performance indicator exceeding a predefined threshold.
7. The method of claim 1 , wherein the predefined trigger event caused the scaling to occur in response to a usage by a virtual machine of a resource of the resources exceeding a predefined threshold.
8. The method of claim 1 , wherein the predefined trigger event caused the scaling to occur in response to an internal metric of the virtual network function exceeding a predefined threshold.
9. The method of claim 8 , wherein the internal metric is a queue length.
10. The method of claim 8 , wherein the internal metric is an amount of dynamic memory not freed.
11. The method of claim 1 , wherein the evaluating indicates that the amount of resources consumed by the virtual network function exceeds the estimated resource capacity associated with the predefined trigger event.
12. The method of claim 11 , wherein the adjusting comprises: increasing, by the processor, the estimated resource capacity associated with the predefined trigger event.
13. The method of claim 1 , wherein the evaluating indicates that an amount of time elapsed between a detection of the predefined trigger event and the completion of the scaling exceeds a predefined threshold.
14. The method of claim 13 , wherein the adjusting comprises: adjusting, by the processor, a predefined threshold for activating the predefined trigger event to cause the predefined trigger event to activate sooner.
15. The method of claim 1 , wherein the evaluating indicates that the value of the key performance indicator is outside a predefined range.
16. The method of claim 15 , wherein the adjusting comprises: adjusting, by the processor, a predefined threshold for activating the predefined trigger event to cause the predefined trigger event to activate sooner.
17. The method of claim 1 , wherein the adjusting targets a value of an efficiency measure that falls within a predefined range.
18. A non-transitory computer-readable medium storing instructions which, when executed by a processor deployed in a network function virtualization infrastructure, cause the processor to perform operations, the operations comprising: determining an amount of resources consumed by a virtual network function subsequent to a scaling of the amount of the resources in response to an occurrence of a predefined trigger event; determining a difference between the amount of resources consumed by the virtual network function subsequent to the scaling and an estimated resource capacity associated with the predefined trigger event; determining a value of a key performance indicator for the virtual network function subsequent to a completion of the scaling; evaluating an efficiency of the predefined trigger event that triggers the scaling, based on the amount of the resources consumed by the virtual network function subsequent to the scaling, and the key performance indicator for the virtual network function subsequent to the completion of the scaling; and adjusting the predefined trigger event based on the evaluating.
19. The non-transitory computer-readable medium of claim 18 , wherein the evaluating indicates that the amount of resources consumed by the virtual network function exceeds the estimated resource capacity associated with the predefined trigger event.
20. A system comprising: a processor deployed in a network function virtualization infrastructure; and a non-transitory computer-readable medium storing instructions which, when executed by the processor, cause the processor to perform operations, the operations comprising: determining an amount of resources consumed by a virtual network function subsequent to a scaling of the amount of the resources in response to an occurrence of a predefined trigger event; determining a difference between the amount of resources consumed by the virtual network function subsequent to the scaling and an estimated resource capacity associated with the predefined trigger event; determining a value of a key performance indicator for the virtual network function subsequent to a completion of the scaling; evaluating an efficiency of the predefined trigger event that triggers the scaling, based on the amount of resources consumed by the virtual network function subsequent to the scaling and the completion of the scaling, and the key performance indicator for the virtual network function subsequent to the completion of the scaling; and adjusting the predefined trigger event based on the evaluating.
Unknown
June 7, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.